© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4568
    Prev
    Next
    INDEX
    Explanations

    candidate selection or options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mira
    -0.08
    oÄį
    -0.08
    udur
    -0.08
    çļĦæĿ¥æºIJ
    -0.08
    té
    -0.07
    æľīéľĢè¦ģçļĦ
    -0.07
    rotn
    -0.07
    .GetInstance
    -0.07
    izedName
    -0.07
    åİŁæĸĩéĵ¾æİ¥
    -0.07
    POSITIVE LOGITS
    åĢĻéĢī
    0.12
     candidate
    0.11
    candidate
    0.11
     competing
    0.11
    _candidate
    0.10
    åĢĻéĢī人
    0.10
     candidacy
    0.10
     candidates
    0.10
     Candidate
    0.09
    Candidate
    0.09
    Activations Density 0.032%

    No Known Activations